咨询与建议

限定检索结果

文献类型

  • 107 篇 会议
  • 62 篇 期刊文献
  • 1 篇 学位论文

馆藏范围

  • 170 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 161 篇 工学
    • 129 篇 计算机科学与技术...
    • 68 篇 电气工程
    • 23 篇 信息与通信工程
    • 23 篇 软件工程
    • 9 篇 控制科学与工程
    • 6 篇 电子科学与技术(可...
    • 2 篇 材料科学与工程(可...
    • 1 篇 机械工程
    • 1 篇 仪器科学与技术
    • 1 篇 建筑学
    • 1 篇 土木工程
  • 65 篇 理学
    • 58 篇 物理学
    • 6 篇 数学
    • 1 篇 化学
    • 1 篇 科学技术史(分学科...
  • 30 篇 文学
    • 16 篇 外国语言文学
    • 1 篇 中国语言文学
  • 24 篇 医学
    • 23 篇 临床医学
    • 1 篇 基础医学(可授医学...
  • 7 篇 管理学
    • 5 篇 管理科学与工程(可...
    • 2 篇 图书情报与档案管...
  • 3 篇 法学
    • 3 篇 社会学
  • 1 篇 历史学
    • 1 篇 考古学
  • 1 篇 艺术学
    • 1 篇 设计学(可授艺术学...

主题

  • 170 篇 text-to-speech s...
  • 11 篇 speech recogniti...
  • 10 篇 prosody
  • 9 篇 speech synthesis
  • 7 篇 voice conversion
  • 7 篇 automatic speech...
  • 6 篇 deep learning
  • 6 篇 deep neural netw...
  • 5 篇 generative adver...
  • 5 篇 unit selection
  • 4 篇 hidden markov mo...
  • 4 篇 natural language...
  • 4 篇 sequence-to-sequ...
  • 4 篇 intonation model...
  • 4 篇 data augmentatio...
  • 3 篇 speech-to-speech...
  • 3 篇 style transfer
  • 3 篇 speaking style
  • 3 篇 intelligibility
  • 3 篇 physiology

机构

  • 4 篇 oregon hlth & sc...
  • 4 篇 univ tokyo
  • 3 篇 univ tokyo grad ...
  • 2 篇 chinese univ hon...
  • 2 篇 fraunhofer sit a...
  • 2 篇 google mountain ...
  • 2 篇 indian inst tech...
  • 2 篇 department of in...
  • 2 篇 nara inst sci & ...
  • 2 篇 usdb signal & co...
  • 2 篇 univ novi sad fa...
  • 2 篇 south china univ...
  • 2 篇 indian inst tech...
  • 2 篇 line corp
  • 2 篇 univ edinburgh c...
  • 2 篇 csir meraka inst...
  • 2 篇 univ rennes cnrs...
  • 2 篇 univ algarve dee...
  • 2 篇 univ patras dept...
  • 2 篇 idiap res inst m...

作者

  • 7 篇 saruwatari hiros...
  • 6 篇 takamichi shinno...
  • 5 篇 nakamura satoshi
  • 4 篇 lazaridis alexan...
  • 4 篇 van santen jan
  • 4 篇 sakti sakriani
  • 4 篇 secujski milan
  • 4 篇 kasparaitis piju...
  • 4 篇 rao k. sreenivas...
  • 3 篇 mporas iosif
  • 3 篇 yamagishi junich...
  • 3 篇 rojc matej
  • 3 篇 ungurean catalin
  • 3 篇 murthy hema a.
  • 3 篇 saito yuki
  • 3 篇 garner philip n.
  • 3 篇 ganchev todor
  • 3 篇 langarani mahsa ...
  • 3 篇 fakotakis nikos
  • 3 篇 kacic zdravko

语言

  • 162 篇 英文
  • 5 篇 其他
  • 2 篇 土耳其文
  • 1 篇 中文
检索条件"主题词=Text-to-speech synthesis"
170 条 记 录,以下是1-10 订阅
排序:
Leveraging Low-Rank Adaptation for Parameter-Efficient Fine-Tuning in Multi-Speaker Adaptive text-to-speech synthesis
收藏 引用
IEEE ACCESS 2024年 12卷 190711-190727页
作者: Hong, Changi Lee, Jung Hyuk Kim, Hong Kook Gwangju Inst Sci & Technol AI Grad Sch Gwangju 61005 South Korea Gwangju Inst Sci & Technol Sch Elect Engn & Comp Sci Gwangju 61005 South Korea AunionAI Co Ltd Gwangju 61005 South Korea
text-to-speech (TTS) technology is commonly used to generate personalized voices for new speakers. Despite considerable progress in TTS technology, personal voice synthesis remains problematic in achieving high-qualit... 详细信息
来源: 评论
ENHANCING LOW-RESOURCE SPOKEN LANGUAGE IDENTIFICATION VIA CROSS-MODALITY RETRIEVAL AND CROSS-LINGUAL text-to-speech synthesis
ENHANCING LOW-RESOURCE SPOKEN LANGUAGE IDENTIFICATION VIA CR...
收藏 引用
2024 Spoken Language Technology Workshop
作者: Ma, Min Wang, Gary Kastner, Kyle Caswell, Isaac Yoon, Charles Rosenberg, Andrew Google Mountain View CA 94043 USA
Spoken language identification (SLID) for low-resource languages remains challenging due to limited data availability. In this paper, we present two novel approaches to address the issue: cross-modality retrieval-base... 详细信息
来源: 评论
text-to-speech synthesis using spectral modeling based on non-negative autoencoder  23
Text-to-speech synthesis using spectral modeling based on no...
收藏 引用
Interspeech Conference
作者: Gorai, Takeru Saito, Daisuke Minematsu, Nobuaki Univ Tokyo Tokyo Japan
This paper proposes a statistical parametric speech synthesis system that uses non-negative autoencoder (NAE) for spectral modeling. NAE is a model that extends non-negative matrix factorization (NMF) as neural networ... 详细信息
来源: 评论
SOCODEC: A SEMANTIC-ORDERED MULTI-STREAM speech CODEC FOR EFFICIENT LANGUAGE MODEL BASED text-to-speech synthesis
SOCODEC: A SEMANTIC-ORDERED MULTI-STREAM SPEECH CODEC FOR EF...
收藏 引用
2024 Spoken Language Technology Workshop
作者: Guo, Haohan Xie, Fenglong Xie, Kun Yang, Dongchao Guo, Dake Wu, Xixin Meng, Helen Chinese Univ Hong Kong Hong Kong Peoples R China Xiaohongshu Inc Shanghai Peoples R China Northwestern Polytech Univ Xian Peoples R China
The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to addres... 详细信息
来源: 评论
StyleFusion TTS: Multimodal Style-Control and Enhanced Feature Fusion for Zero-Shot text-to-speech synthesis  7th
StyleFusion TTS: Multimodal Style-Control and Enhanced Featu...
收藏 引用
7th Chinese Conference on Pattern Recognition and Computer Vision
作者: Chene, Zhiyong Li, Xinnuo Ai, Zhiqi Xu, Shugong Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China
We introduce StyleFusion-TTS, a prompt and/or audio referenced, style- and speaker-controllable, zero-shot text-to-speech (TTS) synthesis system designed to enhance the editability and naturalness of current research ... 详细信息
来源: 评论
FLY-TTS: Fast, Lightweight and High-Quality End-to-End text-to-speech synthesis  25
FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-...
收藏 引用
25th Interspeech Conference
作者: Guo, Yinlin Lv, Yening Dou, Jinqiao Zhang, Yan Wang, Yuehai Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou Peoples R China
While recent advances in text-to-speech synthesis have yielded remarkable improvements in generating high-quality speech, research on lightweight and fast models is limited. This paper introduces FLY-TTS, a new fast, ... 详细信息
来源: 评论
Improving Accented speech Recognition using Data Augmentation based on Unsupervised text-to-speech synthesis  32
Improving Accented Speech Recognition using Data Augmentatio...
收藏 引用
32nd European Signal Processing Conference (EUSIPCO)
作者: Cong-Thanh Do Imai, Shuhei Doddipatla, Rama Hain, Thomas Toshiba Res Europe Cambridge England Tohoku Univ Sendai Miyagi Japan Univ Sheffield Sheffield S Yorkshire England
This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech train... 详细信息
来源: 评论
Retrieval Augmented Generation in Prompt-based text-to-speech synthesis with Context-Aware Contrastive Language-Audio Pretraining  25
Retrieval Augmented Generation in Prompt-based Text-to-Speec...
收藏 引用
25th Interspeech Conference
作者: Xue, Jinlong Deng, Yayue Gao, Yingming Li, Ya Beijing Univ Posts & Telecommun Beijing Peoples R China
Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, an... 详细信息
来源: 评论
The Sound of Language: A Bilingual Analysis of Voice Conversion and text-to-speech synthesis
The Sound of Language: A Bilingual Analysis of Voice Convers...
收藏 引用
2025 IEEE International Conference on Acoustics, speech, and Signal Processing, ICASSP 2025
作者: Choi, Jeong-Eun Schäfer, Karla Steinebach, Martin Fraunhofer SIT ATHENE Darmstadt Germany
With the rise of audio deepfakes, there is an increasing need for comprehensive studies on their generation methods, especially regarding their quality. Areas such as languages beyond English and Chinese, as well as c... 详细信息
来源: 评论
ZET-speech: Zero-shot adaptive Emotion-controllable text-to-speech synthesis with Diffusion and Style-based Models  24
ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-...
收藏 引用
Interspeech Conference
作者: Kang, Minki Han, Wooseok Hwang, Sung Ju Yang, Eunho AITRICS Seoul South Korea Korea Adv Inst Sci & Technol Daejeon South Korea
Emotional text-To-speech (TTS) is an important task in the development of systems (e.g., human-like dialogue agents) that require natural and emotional speech. Existing approaches, however, only aim to produce emotion... 详细信息
来源: 评论